a fair comparison of graph neural networks for graph classification: Difference between revisions
No edit summary |
|||
Line 9: | Line 9: | ||
a large stream of works. As such, several Graph Neural Network models have | a large stream of works. As such, several Graph Neural Network models have | ||
been developed to effectively tackle graph classification. However, experimental | been developed to effectively tackle graph classification. However, experimental | ||
procedures often lack rigorousness and are hardly reproducible. | procedures often lack rigorousness and are hardly reproducible. The authors tried to reproduce | ||
the results from such experiments to tackle the problem of ambiguity in experimental procedures | |||
and the impossibility of reproducing results. They also Standardized the experimental environment | |||
so that the results could be reproduced while using this environment. |
Revision as of 17:46, 9 November 2020
Presented By
Jaskirat Singh Bhatia
Background
Experimental reproducibility and replicability are critical topics in machine learning. Authors have often raised concerns about their lack in scientific publications to improve the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works. As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures often lack rigorousness and are hardly reproducible. The authors tried to reproduce the results from such experiments to tackle the problem of ambiguity in experimental procedures and the impossibility of reproducing results. They also Standardized the experimental environment so that the results could be reproduced while using this environment.